def test_agent_behavior_spec_from_proto():
agent_proto = generate_list_agent_proto(1, [(3, ), (4, )])[0]
bp = BrainParametersProto()
bp.vector_action_size.extend([5, 4])
bp.vector_action_space_type = 0
behavior_spec = behavior_spec_from_proto(bp, agent_proto)
assert behavior_spec.is_action_discrete()
assert not behavior_spec.is_action_continuous()
assert behavior_spec.observation_shapes == [(3, ), (4, )]
assert behavior_spec.discrete_action_branches == (5, 4)
assert behavior_spec.action_size == 2
bp = BrainParametersProto()
bp.vector_action_size.extend([6])
bp.vector_action_space_type = 1
behavior_spec = behavior_spec_from_proto(bp, agent_proto)
assert not behavior_spec.is_action_discrete()
assert behavior_spec.is_action_continuous()
assert behavior_spec.action_size == 6
def test_agent_behavior_spec_from_proto():
agent_proto = generate_list_agent_proto(1, [(3, ), (4, )])[0]
bp = BrainParametersProto()
bp.vector_action_size_deprecated.extend([5, 4])
bp.vector_action_space_type_deprecated = 0
behavior_spec = behavior_spec_from_proto(bp, agent_proto)
assert behavior_spec.action_spec.is_discrete()
assert not behavior_spec.action_spec.is_continuous()
assert [spec.shape for spec in behavior_spec.sensor_specs] == [(3, ),
(4, )]
assert behavior_spec.action_spec.discrete_branches == (5, 4)
assert behavior_spec.action_spec.discrete_size == 2
bp = BrainParametersProto()
bp.vector_action_size_deprecated.extend([6])
bp.vector_action_space_type_deprecated = 1
behavior_spec = behavior_spec_from_proto(bp, agent_proto)
assert not behavior_spec.action_spec.is_discrete()
assert behavior_spec.action_spec.is_continuous()
assert behavior_spec.action_spec.continuous_size == 6
def load_demonstration(
file_path: str,
) -> Tuple[BehaviorSpec, List[AgentInfoActionPairProto], int]:
"""
Loads and parses a demonstration file.
:param file_path: Location of demonstration file (.demo).
:return: BrainParameter and list of AgentInfoActionPairProto containing demonstration data.
"""
# First 32 bytes of file dedicated to meta-data.
file_paths = get_demo_files(file_path)
behavior_spec = None
brain_param_proto = None
info_action_pairs = []
total_expected = 0
for _file_path in file_paths:
with open(_file_path, "rb") as fp:
with hierarchical_timer("read_file"):
data = fp.read()
next_pos, pos, obs_decoded = 0, 0, 0
while pos < len(data):
next_pos, pos = _DecodeVarint32(data, pos)
if obs_decoded == 0:
meta_data_proto = DemonstrationMetaProto()
meta_data_proto.ParseFromString(data[pos : pos + next_pos])
if (
meta_data_proto.api_version
not in SUPPORTED_DEMONSTRATION_VERSIONS
):
raise RuntimeError(
f"Can't load Demonstration data from an unsupported version ({meta_data_proto.api_version})"
)
total_expected += meta_data_proto.number_steps
pos = INITIAL_POS
if obs_decoded == 1:
brain_param_proto = BrainParametersProto()
brain_param_proto.ParseFromString(data[pos : pos + next_pos])
pos += next_pos
if obs_decoded > 1:
agent_info_action = AgentInfoActionPairProto()
agent_info_action.ParseFromString(data[pos : pos + next_pos])
if behavior_spec is None:
behavior_spec = behavior_spec_from_proto(
brain_param_proto, agent_info_action.agent_info
)
info_action_pairs.append(agent_info_action)
if len(info_action_pairs) == total_expected:
break
pos += next_pos
obs_decoded += 1
if not behavior_spec:
raise RuntimeError(
f"No BrainParameters found in demonstration file at {file_path}."
)
return behavior_spec, info_action_pairs, total_expected
def _update_behavior_specs(self, output: UnityOutputProto) -> None:
init_output = output.rl_initialization_output
for brain_param in init_output.brain_parameters:
# Each BrainParameter in the rl_initialization_output should have at least one AgentInfo
# Get that agent, because we need some of its observations.
agent_infos = output.rl_output.agentInfos[brain_param.brain_name]
if agent_infos.value:
agent = agent_infos.value[0]
new_spec = behavior_spec_from_proto(brain_param, agent)
self._env_specs[brain_param.brain_name] = new_spec
logger.info(f"Connected new brain:\n{brain_param.brain_name}")
